feat: ai chat endpoint added

Backend/app/api/v1/api.py

@@ -1,5 +1,5 @@
 from fastapi import APIRouter
-from app.api.v1.endpoints import auth, quiz
+from app.api.v1.endpoints import auth, quiz, notes
 
 api_router = APIRouter()
 
@@ -17,3 +17,9 @@ api_router.include_router(
     prefix="/quiz",
     tags=["quiz"]
 )
+
+api_router.include_router(
+    notes.router,
+    prefix="/notes",
+    tags=["notes"]
+)

Backend/app/api/v1/endpoints/notes.py

@@ -1,23 +1,26 @@
 from fastapi import APIRouter, Depends, HTTPException, status
-from chromadb import AsyncHttpClient
+from sqlalchemy.ext.asyncio import AsyncSession
 from app.models import User
-from app.api.deps import get_db, get_current_user, get_chroma_client
-from app.schema import Quiz_input, QuizOutput, IngestRequest
+from app.api.deps import get_db, get_current_user
+from app.schema import ChatMessage, AI_chat_input
 from .prompts import SYSTEM_PROMPT
-from fastapi import APIRouter, Depends, HTTPException
-from chromadb.api.models.Collection import Collection # Import Collection type
-from app.api.deps import get_chroma_collection
-from app.llm import call_llm
+from app.llm import call_llm, stream_chat
 import uuid
+from fastapi.responses import StreamingResponse
 
 
 
 router = APIRouter(prefix="/notes")
 
-@router.post("/ai_chat", status_code=status.HTTP_201_CREATED)
+@router.post("/stram_chat", response_class=StreamingResponse)
 async def ai_chat(
-    Input_model: IngestRequest, 
-    collection: Collection = Depends(get_chroma_collection), 
+    Input_model: AI_chat_input, 
+    # db: AsyncSession = Depends(get_db),
     current_user: User = Depends(get_current_user)
 ):
-    pass
+    messages_dict = [msg.model_dump() for msg in Input_model.messages]
+
+    return StreamingResponse(
+        stream_chat(messages_dict, Input_model.context),
+        media_type="text/plain"
+    )

Backend/app/llm.py

@@ -4,8 +4,9 @@ from pydantic import BaseModel, Field
 from typing import List, Optional, Any
 from app.schema.models import QuizOutput, QuizQuestion
 from app.config import settings
+from openai import AsyncOpenAI
 
-client = OpenAI(
+client = AsyncOpenAI(
     base_url="https://api.groq.com/openai/v1",
     api_key=settings.GROQ_API_KEY
 )
@@ -32,4 +33,51 @@ async def call_llm(prompt:str):
 
     except Exception as e:
         print(f"Error calling LiteLLM/Gemini: {e}")
-        raise e
+        raise e
+
+
+
+async def stream_chat(messages:List[dict], context:str):
+    system_instruction = {
+        "role": "system", 
+        "content": "You are a helpful AI assistant. Answer the user's question strictly based on the provided context."
+    }
+    
+    conversation_history = [msg.copy() for msg in messages]
+
+    if conversation_history and conversation_history[-1]['role'] == 'user':
+        last_user_msg = conversation_history[-1]
+        # Rewrite the content to: Context + \n\n + Question
+        last_user_msg['content'] = (
+            f"Here is the context/notes you must use:\n"
+            f"---------------------\n"
+            f"{context}\n"
+            f"---------------------\n\n"
+            f"User Question: {last_user_msg['content']}"
+        )
+    else:
+        # Fallback: If for some reason there is no user message, add one.
+        conversation_history.append({
+            "role": "user", 
+            "content": f"Context:\n{context}\n\nPlease analyze this."
+        })
+
+    # 3. Combine System + Modified User History
+    full_history = [system_instruction] + conversation_history
+
+    try:
+        # Ensure you are using the async_client initialized earlier
+        stream = await client.chat.completions.create(
+            model="openai/gpt-oss-20b", # Recommended for speed/quality on Groq
+            messages=full_history,
+            temperature=0.7,
+            stream=True 
+        )
+
+        async for chunk in stream:
+            if chunk.choices[0].delta.content:
+                yield chunk.choices[0].delta.content
+
+    except Exception as e:
+        print(f"Error in chat stream: {e}")
+        yield f"Error: {str(e)}"

Backend/app/schema/__init__.py

@@ -1,3 +1,3 @@
-from app.schema.models import UserCreate, Token, LoginRequest, Quiz_input, QuizOutput, IngestRequest
+from app.schema.models import UserCreate, Token, LoginRequest, Quiz_input, QuizOutput, IngestRequest, ChatMessage, AI_chat_input
 
-__all__ = ["UserCreate", "Token", "LoginRequest", "Quiz_input", "QuizOutput", "IngestRequest"]
+__all__ = ["UserCreate", "Token", "LoginRequest", "Quiz_input", "QuizOutput", "IngestRequest", "ChatMessage", "AI_chat_input"]

Backend/app/schema/models.py

@@ -53,15 +53,12 @@ class IngestRequest(BaseModel):
 # #--------Notes models--------#
 
 class ChatMessage(BaseModel):
-    role: Literal['user', 'assistant', 'system'] = Field(description="The sender of the message. Must be 'user', 'assistant', or 'system'.")
-    content: str=Field(..., min_length=1, description="The text content of the message.")
+    role: Literal["user", "assistant", "system"] = Field(..., description="Role of the message sender")
+    content: str = Field(..., min_length=1, description="Message content")
 
 class AI_chat_input(BaseModel):
-    messages = List[ChatMessage] = Field(
-        ...,
-        min_length=1,
-        description="The complete conversation history (list of messages) to send to the LLM."
-    )
+    messages: List[ChatMessage] = Field(..., description="Conversation history")
+    context: str = Field(..., description="The content of the note/document to chat about")
     session_id: str | None = Field(
         None, description="The unique ID of the current chat session (optional)."
     )